Connect public, paid and private patent data with Google Patents Public Datasets

Method and apparatus for summarizing documents according to theme

Download PDF

Info

Publication number
US5384703A
US5384703A US08085385 US8538593A US5384703A US 5384703 A US5384703 A US 5384703A US 08085385 US08085385 US 08085385 US 8538593 A US8538593 A US 8538593A US 5384703 A US5384703 A US 5384703A
Authority
US
Grant status
Grant
Patent type
Prior art keywords
document
list
summary
characters
character
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US08085385
Inventor
M. Margaret Withgott
Douglass R. Cutting
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xerox Corp
Original Assignee
Xerox Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Grant date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30Information retrieval; Database structures therefor ; File system structures therefor
    • G06F17/3061Information retrieval; Database structures therefor ; File system structures therefor of unstructured textual data
    • G06F17/30716Browsing or visualization
    • G06F17/30719Summarization for human users

Abstract

A summary is automatically formed by selecting regions of a document. Each selected region includes at least two members of a seed list. The seed list is formed from a predetermined number of the most frequently occurring complex expressions in the document that are not on a stop list. If the summary is too long, the region-selection process is performed on the summary to produce a shorter summary. This region-selection process is repeated until a summary is produced having a desired length. Each time the region selection process is repeated, the seed list members are added to the stop list and the complexity level used to identify frequently occurring expressions is reduced.

Description

BACKGROUND OF THE INVENTION

1. Field of the Invention

The invention relates to methods and apparatus for automatically producing summaries of documents and, in particular, utilizing simple natural language processing and relying on statistical properties of text to produce such summaries.

2. Description of Related Art

Document summaries assist in the review of documents because entire documents do not need to be read. Additionally, document summaries can reduce translation costs when reviewing one or more documents in a foreign language because only the document summary--not the entire document--needs to be translated. After reviewing the translated document summary, the reviewer can determine whether the entire document should be translated.

When documents are not provided with a summary, it is necessary to produce a summary of the document to obtain the benefits discussed above. It is desirable to produce document summaries automatically so that people do not have to read an entire document to produce a summary. Such automatic summaries should accurately reflect the main theme(s) in the document to assist people in deciding correctly whether to read (and/or have translated) the entire document.

Two basic computational techniques exist for automatic document summarization. The first intensively uses natural language processing and semantic network creation. The second uses simple natural language processing and then relies on statistical properties of the text.

The first technique is computationally expensive. Additionally, creating semantically correct summaries is difficult and error prone. Typically, a domain must be known in advance in order to perform adequate semantic modeling. Such techniques may not be used on ordinary text, unrestricted in content.

"Automatic Text Processing"; Gerald Salton; Addison-Wesley; 1989 discloses a summarization technique of the second type. Text words from a corpus of documents are isolated. Words used in titles, figures, captions and footnotes are flagged as title words. The frequency of occurrence of the remaining text words within the document corpus is determined. Word weights are determined based on the location and frequency of occurrence of the words in individual documents and in the document corpus. Phrase weights are determined for coocurring words (phrases) in sentences of a document. The sentences in each document are then scored based on the weights of the words and phrases in each sentence. A number of topscoring sentences are then selected from a document to produce a summary having a predetermined length.

The technique described-by Salton uses a corpus of documents to calibrate the weights of the words and phrases. Thus, the term weights are not customized to an individual document. This could result in the inclusion of sentences in a document's summary that do not assist in describing a theme of the document. Additionally, an overly-narrow cross section of the document may be extracted because the technique of Salton creates the document summary from a single pass through the document. The selection of only the highest scoring sentences may lead to a disjointed summary that does not convey a cogent theme.

SUMMARY OF THE INVENTION

Methods and apparatus, according to the invention, form a summary by selecting regions of a document. Each selected region includes at least two members of a seed list. The seed list is formed from a predetermined number of the most frequently occurring complex expressions in the document that are not on a stop list. If the summary is too long, the region-selection process is performed on the summary to produce a shorter summary. This region selection process is repeated until a summary is produced having a desired length. Each time the region selection process is repeated, the seed list members are added to the stop list and the complexity level used to identify frequently occurring expressions is reduced.

When the text is formed from sentences arranged in paragraphs, each selected region preferably corresponds to a sentence containing at least two members of the seed list, and the immediately preceding and following sentences contained in the same paragraph.

Regions located in the title, first paragraph and/or last paragraph of the document that are included in the first summary can be maintained in the final summary because they usually relate to the theme of the document. Word stemming can also improve results.

Commonly used function words such as conjunctions joining words or phrases, articles introducing noun phrases, and modals modulating the meaning of verbs initially can be included in the stop list to improve efficiency. Alternatively, the stop list can be empty for the first iteration of the region-selection process.

The invention is particularly useful with documents written in the form of prose, as opposed to degenerate text such as phone books, spread sheets, dictionaries, etc., which do not usually convey a theme.

The invention is applicable to text written in a variety of languages. In text using roman characters, such as English, the expressions correspond to words, and the seed list includes the most frequently occurring lengthy words. For languages that employ chinese characters (such as Mandarin), expressions correspond to characters and character strings. The seed list includes the most frequently occurring complex characters and character strings, where complexity is defined by the number of strokes in the character or character string. Complex expressions in Japanese language documents correspond to long hiragana/katakana/roman character strings and to chinese (kanji) characters and character strings having a predetermined minimum number of strokes. The word or character string length and the complex character or character string stroke number is reduced each time the region-selection process is performed.

The resulting summaries are comprised of wellformed sentences (assuming the original document contained such sentences) that convey the theme of the document. No natural language parsing or semantic networks are required. Thus, computational costs are low.

BRIEF DESCRIPTION OF THE DRAWINGS

The invention will be described in conjunction with the following drawings in which like reference numerals refer to like elements and wherein:

FIG. 1 is a block diagram of an apparatus according to the invention for carrying out document summarization;

FIG. 2 is a flowchart of the general document summarization method of the invention;

FIG. 3 is a partial flowchart of the FIG. 2 method adapted for English-language documents;

FIG. 4 is a partial flowchart of the FIG. 2 method adapted for Japanese language documents;

FIG. 5 is an illustrative Japanese language stop list;

FIG. 6 is a partial flowchart of the FIG. 2 method adapted for Chinese-language documents;

FIG. 7 is a list of kanji characters classified according to number of strokes; and

FIGS. 8-12 illustrate a stop list of commonly used kanji characters and character strings.

DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS

The invention provides a summary of a document that conveys the theme(s) of the document. The invention automatically locates regions (e.g., sentences) in the document that convey the conceptually dominate theme(s) of the document, and then forms a summary from those regions. The invention operates on the theory that regions of the document containing frequently used complex expressions pertain to the theme of the document, and therefore are useful for forming a thematic document summary.

The invention is useful with most types of documents and, particularly, with documents written in the form of prose, as compared with degenerate documents such as telephone directories, spreadsheets and dictionaries, which usually do not convey a theme.

The invention is useful with documents written in numerous languages including English, Japanese and Chinese. In English-language documents, expressions correspond to words, and complexity is quantified by word length. In languages that employ chinese characters (such as Mandarin), expressions correspond to characters and character strings, and complexity is quantified by the number of strokes in a character or character string. In Japanese language-documents, expressions correspond to hiragana/katakana/roman character strings, kanji characters, and kanji character strings. In Japanese language documents, complexity is quantified by the length of hiragana/katakana/roman character strings and the number of strokes contained in kanji characters and kanji character strings.

With reference to FIG. 1, the theme summarization method of the invention is performed either on an electronic (bitmap) image of an original document or on a document stored as character codes (e.g., ASCII data). The method is performed by a special or general purpose digital computer 100 that uses procedures stored in a memory 110. The electronic document (bitmap image data or character code data) is input to computer 100 by input device 80. Input device 80 can be, for example, a word processing station, a disk drive, a modem, a scanner with or without an optical character recognizer (OCR), etc. The document summary can be output from computer 100 to output device 90. Output device 90 can include an output display 92, a printing device 98, or a memory or other form of storage device. Output display 92 can include a touchscreen 94 so that a user can interact with computer 100. Means other or in addition to touchscreen 94 can be provided for supplying commands or other information to computer 100. For example, a keyboard 96 and/or a mouse 115 can be used to interact with computer 100.

FIG. 2 is a flowchart illustrating an embodiment of the theme summarization process.

A number of preliminary steps are performed. In an initialization step, S10, a complexity level and a seed list size are predetermined. Such parameters can be input by a user, or default values can be used. Additionally, initial members of a stop list which is stored in computer memory can be defined in S10. Next, in S20 a document or plurality of documents are input,and stored in computer memory. Although a plurality of documents can be input, the method preferably creates a document summary without using any information relating to the other documents (unlike Salton). Documents can be input as character codes, e.g., from a word processor, or as bitmap images, e.g., from a scanner without an OCR.

Next, a preprocessing step, S30, is performed. The preprocessing step at least includes tokenizing the document in S32. Tokenizing comprises breaking the document into a plurality of expressions. For example, in an English-language document, the tokenizing step corresponds to identifying all words in the document. If any expressions are initially placed on the stop list, these expressions are then removed from the document, or otherwise flagged relative to the remaining text in S34. Initial members of the stop list can be, for example, frequently used expressions that serve as syntactic glue such as, for example, conjunctions joining words or phrases, articles introducing noun phrases, and modals modulating the meaning of verbs, etc. Additionally, a stemming operation, S36, can be performed on the document expressions.

After preprocessing the document, the theme summarization process can begin. In step S40, the frequency of occurrence of complex expressions, not contained in the stop list, and located in the document is determined. In step S50, a seed list is formed from a predetermined number, S, of expressions having the highest,frequency as determined in step S40. The seed list is stored in computer memory and then used to identify regions of the document that likely relate to the theme(s) of the document. In step S60, regions of the document are selected based on the occurrence of two or more seed list members in those regions. In a preferred embodiment, where the document is in the form of plural sentences forming plural paragraphs, each region corresponds to a sentence containing at least two members of the seed list and the immediately preceding and following sentences located in the same paragraph. Inclusion of the immediately preceding and following sentences provides context and makes the resulting summary read better. If the document does not include plural sentences (which may be the case in some documents written in languages other than English), the region selection criteria can be the location of two members of the seed list within a predetermined proximity of one another. The selected region preferably would correspond to the seed list members, the intervening text, and some predetermined amount of text preceding and following the seed list members. In step S70, a summary of the document is formed from the selected regions and stored in computer memory. This summary could be formed by extracting the selected regions from the document, or by other means.

The summary formed from this first iteration of steps S40-S70 typically results in the elimination of approximately 70% of the text from the original document. Depending on the length of the original document, one iteration of steps S40-S70 may produce a summary short enough to form the final document summary. Typically, the document summary is required to have a length of one page or less.

In S80, a determination is made as to whether the summary produced in S70 has the desired length. The desired length can be input by a user, or can be a predetermined default length. If the result of S80 is affirmative, flow proceeds to S100 where the summary is output as the document summary. The document summary can be output to display 92, printer 98, or to a memory. The output document summary could be output as a result of a text search process so that an operator does not have to read an entire document identified during a search. Instead, only the document summary need be reviewed. The document summary could be invoked automatically by operator selection of a summarize document button (as opposed to an output entire document button) during searching.

If the result of S80 is negative, flow proceeds to S90. In S90, the seed list members are added to the stop list. Next, in S95, the complexity level is reduced. Flow then returns to S40 for a second iteration of steps S40-S80. This second iteration is performed on the summary, previously produced in S70. However, a subset of the regions previously selected in S60 will be selected because the previous members of the seed list are now on the stop list and because the complexity level has been reduced.

Steps S40-S80 will continue to repeat until a summary is formed having the desired length. Each time steps S40-S80 are repeated, the size of the stop list increases (as former members of the seed list are added to the stop list) and the complexity level is reduced.

The output of the process can be modified by tagging regions located in the first and/or last paragraphs of the document that were selected the first time S60 was performed and maintaining these regions in the final output document summary. This additional step or steps can improve the output document summary because the first and last paragraphs of the document typically relate to the overall theme of the document.

Due to the iterative nature of the invention, cogent themes emerge in the resulting document summary. Because the number of lines in the document is pared down in successive steps based on whether those lines have in the past, or now have, words in them that are members of a seed list, the lines that remain do so because frequent stop words (such as "a ", "the", "and", etc.) were permitted to form the seed list, or if there were successive homonyms in the original document (e.g., if the document had an unusual number of types of words such as "bank" (river banks or financial institutions)), and an unusually high number of tokens of those homonyms.

Examples of the invention as applied to English, Japanese, and Chinese language documents will now be described. The written embodiments of expressions in these languages differs and, therefore, the way in which text is classified as complex differs between these languages. In English-language documents, expressions are conveyed in the form of words. Thus, complex expressions correspond to lengthy words. The Chinese-language uses characters to represent expressions. A character can correspond to a single word or to, plural words (a phrase). Additionally, characters can be compounded in the Chinese language. Accordingly, expressions correspond to one or more characters. Complexity is determined by the number of strokes contained in the character or character string. The Japanese language uses Chinese characters and other characters (roman characters and syllabaries such as hiragana and katakana characters) to form expressions that may correspond to one or more words. Thus, the stroke complexity of kanji characters and character strings, and the character length complexity of hiragana, katakana and roman character strings are considered for Japanese language documents.

FIG. 3 is a partial flowchart of the FIG. 2 method illustrating the specific steps used for forming a summary of an English-language document. In such a document, the method is performed based on the frequency of occurrence of complex words in the document. Complex words are defined as words having a length (i.e., number of characters) equal to or greater than some predetermined length.

In the initialization step, S10', an initial value, X, is assigned to the predetermined word length variable, L. Additionally, a value, Y, is assigned to the parameter S that defines the number of members in the seed list. In a preferred embodiment, S=6, and, initially, L=8. These predetermined values can be input by the operator or can be default values. Referring to FIG. 2, a document is then input in S20, and the preprocessing step or steps are performed in S30. Preprocessing includes at least the tokenization step S32. Additionally, the stop list can be initialized to contain commonly used words, which are then removed from the document in S34. Alternatively, the stop list is initially empty. Stemming operations can also be performed in S36.

Referring to FIG. 3, in S40', the number of occurrences of words having a length of at least L and not contained on the stop list are determined. In S50', S words having the highest frequency, as determined in S40', are placed in the seed list. Next, in S60', sentences containing at least two members of the seed list and the immediately preceding and following sentences are selected. These selected sentences are then used to form a summary in S70. Usually, the sentences are maintained in their original reading order when placed in the summary. If multiple sentence triplets are from a single paragraph of the original document, they are placed in a single paragraph of the summary. If sentence triplets are from different paragraphs in the original document, they can be placed in different paragraphs of the summary.

In S80', a determination is made as to whether the summary has a length of one page or less. Of course, a length other than one page can be used as the predetermined summary length. If the result of S80' is affirmative, the summary is output as a document summary in S 100. If the result of S80' is negative, the six words on the seed list are added to the stop list in S90, and in S95', the value of L is decreased by one. Thus, the second time S40' is performed, the frequency of words having a length of seven or more (and not contained on the stop list) is determined.

The FIG. 3 method can be used on documents represented as coded ASCII data, or on undecoded bitmap images. If bitmap images are used, morphological image processing techniques can be used, for example, to compare word shapes in determining the frequency of occurrence of complex words.

FIG. 4 illustrates the method of FIG. 2 adapted for use with Japanese language documents. Japanese differs from other languages in that it makes systematic use of four distinct writing systems: a roman alphabet, two syllabaries (hiragana and katakana) and Chinese (kanji) characters. Japanese is also written both horizontally and vertically, and there is usually no inter-word space.

Initially, the reading order of the text (i.e., vertical verses horizontal) is determined. This information can be input to computer 100, or can be determined using known automatic processes. Machine readable text is usually in a canonical form. The general method disclosed in FIG. 2 is then adapted for use with Japanese by defining two types of complex expressions. A first type of expression is defined by character strings of hiragana, katakana or roman characters. The complexity of these character strings is determined based on their length, similar to the English-language embodiment described above. Kanji characters are treated differently. The complexity of kanji characters and frequently used kanji character strings is defined by the number of strokes in the kanji character or character string. FIG. 7 is a stroke table classifying kanji characters by stroke number (15, 16, 17, 18 etc.). Preferably, the Japanese language document is stored as character code so that the character type (i.e., hiragana, katakana, roman, kanji) is determined from the character code.

In the initialization step, S10", a value, X, is assigned to the character string length parameter, L. A value Y is assigned to the seed list length parameter, S. A stroke complexity parameter C must also be initialized. Preferably, the stroke complexity parameter C is normalized with respect to the length complexity parameter, L. Preferably, complex kanji characters or kanji character strings have a greater number of strokes than complex hiragana/katakana/roman character strings have characters. Accordingly, the stroke complexity parameter, C, is greater than the length complexity parameter, L. Thus, C is initialized to a value equal to L times a normalization variable, a, having a value greater than one. For example, a=2. Thus, in one preferred embodiment, initially, L=8 and C=16. The initial values of L, S, C, and a can be defined by a user or can be determined by default.

Referring to FIG. 2, in step S20, a Japanese language document is input. In preprocessing step S30, at least the tokenization step S32 is performed.

In the tokenization step, character strings are identified as hiragana character strings, katakana character strings, roman character strings and kanji character strings. Preferably, in step S34, character strings contained on a stop list are removed. FIG. 5 is an illustrative stop list for a Japanese language document.

Next, referring to FIG. 4, in S40", the frequency of complex expressions are determined, wherein an expression corresponds to hiragana, katakana and roman character strings, and kanji characters and kanji character strings. First, in S41, the frequency of hiragana/katakana/roman character strings having a length of at least L, and not included on the stop list is determined. Next, in S42, the frequency of kanji and kanji character strings having at least C strokes, and not included on the stop list, is determined. The seed list is formed in S50" by placing the S highest frequency hiragana/katakana/roman character strings and kanji characters and character strings in the seed list.

Next, in S60", regions of the document relating to the document theme(s) are selected. If the Japanese language document contained sentences organized as paragraphs, as illustrated in S61a, regions are selected in a manner similar to that described above with respect to English-language documents. As an alternative, as illustrated in S61b, regions of text can be selected based upon the occurrence of at least two seed list members within a certain proximity of each other, along with a predetermined amount of surrounding text.

Next, flow proceeds to S70 in which the document summary is formed. The remaining steps are similar to those described above with respect to FIGS. 2 and 3, except that in S95", the value of L is decreased by one, and then the value of C is redetermined based upon the new value of L.

Next, referring to FIG. 6, adaptation of the FIG. 2 method for use with documents written in a language that employs chinese characters will be described. The document is preferably produced as a file containing character codes. Alternatively, a scanned document should be recognized and converted into character codes prior to performing the invention. For languages employing chinese characters, complex expressions correspond to characters and character strings having a predetermined minimum number of strokes. As with the embodiments described above, useful expressions correspond to those which are the most frequently used in a document and which do not exist in a stop list of commonly used expressions. FIGS. 8-12 illustrate a stop list of commonly used expressions that can be used to initially remove expressions that do not contribute to producing a theme summary from a document having chinese characters. Additionally, because of a propensity for compounding, strings of chinese characters as well as individual characters should be considered as possible expressions. However, because there is no inter-word spacing with chinese characters, it can be difficult to determine when an expression represented by a plurality of characters begins and ends. The invention addresses these difficulties with relative ease because it relies upon the statistics of frequently occurring complex expressions.

In the initialization step, S10"', a value, X, is assigned to a character string length parameter, L. A value, Y, is assigned to the seed list parameter, S. A value, Z, is assigned to the complexity parameter, C. These values can be input by an operator or can be default values.

The complex expression frequency determination step, S40'", is as follows. In S46, the frequency of all character strings having a length of at least L and not contained on the stop list is determined. In theory, this could mean determining all possible sub-strings for the entire document because, typically, no inter-word spacing is included. In practice, however, this is facilitated by breaking the text according to punctuation and paragraph structure, and also at certain common characters representing morphemes that play a purely syntactic role. In S47, all character strings having less than C strokes are eliminated. In S48, the frequency of all characters having at least C strokes, and not included on the stop list, is determined. Thus, S40'" determines the frequency of all complex characters (having at least C strokes) and all complex character strings (having at least C strokes) not contained on the stop list.

In S50'", the S highest frequency complex characters and complex character strings are then placed in the seed list. The remaining steps are similar to those described above with respect to FIG. 2 except that in S95'", the value of C is decreased by one for each iteration of the procedure.

In a preferred embodiment, initially, S=6 and C=17.

While this invention has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications and variations will be apparent to those skilled in the art. Accordingly, the preferred embodiments of the invention as set forth herein are intended to be illustrative, not limiting. Various changes may be made without departing from the spirit and scope of the invention as defined in the following claims.

Claims (55)

What is claimed is:
1. An automated, computer implemented method of electronically processing a document stored in a memory of a computer, said document containing text represented by characters, said method comprising the steps of:
a) using the computer, automatically determining a frequency of occurrence of expressions in the document not contained in a stop list and having at least a first predetermined level of complexity, said stop list stored in the memory of said computer;
b) using the computer, automatically forming a seed list comprised of a second predetermined number of the most frequently occurring expressions determined in step (a), said seed list stored in said memory of said computer;
c) using said computer, automatically forming a summary of the document comprised of regions in the document containing at least two members of said seed list, said summary stored in said memory of said computer; and
d) using said computer, automatically repeating steps (a)-(c) on said summary until a length of said summary is no greater than a predetermined length, each time steps (a)-(c) are repeated, adding the members of said seed list to said stop list and reducing said first predetermined level of complexity.
2. The method of claim 1, wherein each expression is represented in the document as at least one character.
3. The method of claim 2, wherein at least some of said expressions are represented as character strings.
4. The method of claim 3, wherein the level of complexity of each character string is determined by said computer based on a length of said character string.
5. The method of claim 1, wherein the level of complexity of each expression is determined by said computer based on a length of said expression.
6. The method of claim 1, wherein the level of complexity of each expression is determined by said computer based on a number of strokes contained in said expression.
7. The method of claim 1, wherein each expression is a word, so that in step (a) said computer determines a frequency of occurrence of words in the document.
8. The method of claim 7, wherein the complexity of each word is determined by said computer based on a length of said word.
9. The method of claim 7, further comprising, using said computer, performing a word-stemming operation on words in said document prior to performing step (a).
10. The method of claim 1, wherein each of said regions comprises a portion of the document containing at least two of said members of said seed list.
11. The method of claim 10, wherein said portion is a sentence, so that each of said regions includes a sentence containing at least two of said members of said seed list.
12. The method of claim 1, wherein each of said regions comprises a sentence containing at least two of said members of said seed list and immediately preceding and following sentences located in a same paragraph as said sentence containing at least two of said members of said seed list.
13. The method of claim 1, further comprising including in a final summary of said document, any regions located in a first paragraph of said document, and contained in a summary of the document a first time step (c) is performed by said computer.
14. The method of claim 1, further comprising including in a final summary of said document, any regions located in a last paragraph of said document, and contained in a summary of the document a first time step (c) is performed by said computer.
15. The method of claim 1, further comprising including in a final summary of said document, any regions located in a first and a last paragraph of said document, and contained in a summary of the document a first time step (c) is performed by said computer.
16. The method of claim 1, wherein said stop list is empty before step (a) is performed a first time.
17. The method of claim 1, wherein said stop list includes a plurality of predefined stop expressions before step (a) is performed a first time.
18. The method of claim 17, wherein said predefined stop expressions include conjunctions, articles and modals.
19. The method of claim 1, wherein said summary is formed using said computer by extracting said regions from said document and constructing said summary from said extracted regions.
20. The method of claim 19, wherein said extracted regions are maintained in a same order in said summary as in the document.
21. The method of claim 1, wherein said second predetermined number is at least six.
22. The method of claim 1, wherein said predetermined length of said summary is no greater than one page.
23. The method of claim 1, further comprising using said computer, automatically outputting said summary when a length of said summary is no greater than said predetermined length.
24. The method of claim 23, wherein said summary is output on a display screen.
25. The method of claim 23, wherein said summary is output by a printer.
26. The method of claim 1, wherein said document includes roman characters, and step (a) comprises, using said computer, determining a frequency of occurrence of words defined by said roman characters in the document not contained in said stop list and having at least a predetermined number of said roman characters.
27. The method of claim 26, wherein said document is an English-language document.
28. The method of claim 1, wherein said document is a Japanese language document containing text represented by hiragana characters, katakana characters, roman characters, and kanji characters, and wherein step (a) includes:
using said computer, determining a frequency of occurrence of character strings in the document not contained in said stop list, containing at least one of said hiragana, katakana, and roman characters, and having at least a predetermined number of characters.
29. The method of claim 1, wherein said document is a Japanese language document containing text represented by hiragana characters, katakana characters, roman characters, and kanji characters, and wherein step (a) includes:
using said computer, determining a frequency of occurrence of kanji characters and repeated kanji character strings in the document not contained in said stop list, and containing at least a predetermined number of strokes.
30. The method of claim 1, wherein said document is a Chinese-language document containing text represented by chinese characters, and wherein:
step (a) includes using said computer, determining:
a frequency of occurrence of chinese characters in the document not contained in said stop list and having a predetermined number of strokes, and
a frequency of chinese character strings in the document not contained in said stop list, having at least a third predetermined number of chinese characters, and having said predetermined number of strokes; and
step (b) includes forming said seed list from said second predetermined number of the most frequently occurring characters and character strings determined in step (a).
31. An automated, computer implemented method of electronically processing a document stored in a memory of a computer, said document containing words represented by roman characters, said method comprising the steps of:
a) using the computer, automatically determining a frequency of occurrence of words in the document having at least a first predetermined number of characters and not contained in a stop list that is stored in the memory of the computer;
b) using the computer, automatically forming a seed list comprised of a second predetermined number of the most frequently occurring words in the document having at least said first predetermined number of characters, said seed list stored in the memory of the computer;
c) using the computer, automatically forming a summary of the document comprised of regions in the document containing at least two words in said seed list, said summary stored in the memory of the computer; and
d) using the computer, automatically repeating steps (a)-(c) on said summary until a length of said summary is no greater than a predetermined length, each time steps (a)-(c) are repeated, adding the words on said seed list to said stop list and reducing a value of said first predetermined number.
32. The method of claim 31, wherein said document is an English-language document.
33. The method of claim 31, further comprising using said computer, performing a word-stemming operation on words in said document prior to performing step (a).
34. The method of claim 31, wherein said regions include at least a sentence containing said at least two words in said seed list.
35. The method of claim 31, wherein each of said regions comprises a sentence containing said at least two words in said seed list and immediately preceding and following sentences located in a same paragraph as said sentence containing said at least two words in said seed list.
36. The method of claim 31, further comprising including in a final summary of said document, any regions located in a first paragraph of said document, and contained in a summary of the document a first time step (c) is performed by the computer.
37. The method of claim 31, further comprising including in a final summary of said document, any regions located in a last paragraph of said document, and contained in a summary of the document a first time step (c) is performed by the computer.
38. The method of claim 31, wherein said stop list is empty before step (a) is performed a first time.
39. The method of claim 31, wherein said stop list includes a plurality of predefined stop words before step (a) is performed a first time.
40. The method of claim 31, further comprising using said computer, automatically outputting said summary when a length of said summary is no greater than said predetermined length.
41. An automated, computer implemented method of electronically processing a Japanese language document stored in a memory of a computer, said document containing text represented by hiragana characters, katakana characters, roman characters, and kanji characters, said method comprising the steps of:
a) using the computer, automatically determining a frequency of occurrence of character strings in the document not contained in a stop list, containing at least one of said hiragana, katakana, and roman characters, and having at least a first predetermined number of characters, said stop list stored in the memory of the computer;
b) using the computer, automatically determining a frequency of occurrence of kanji characters and repeated kanji character strings in the document not contained in said stop list, and containing at least a second predetermined number of strokes;
c) using the computer, automatically forming a seed list stored in the memory of the computer, said seed list comprised of a third predetermined number of the most frequently occurring:
character strings in the document having at least said first predetermined number of characters, and
kanji characters and repeated kanji character strings in the document having at least said second predetermined number of strokes;
d) using the computer, automatically forming a summary of the document comprised of all sentences in the document containing at least two members of said seed list and surrounding sentences, said summary stored in the memory of the computer; and
e) using the computer, automatically repeating steps (a)-(d) on said summary until a length of said summary is no greater than a predetermined length, each time steps (a)-(d) are repeated, adding the members on said seed list to said stop list and reducing values of said first and second predetermined numbers.
42. An automated, computer implemented method of electronically processing a Chinese-Language document stored in a memory of a computer, said document containing text represented by Chinese characters, said method comprising the steps of:
a) using the computer, automatically determining a frequency of occurrence of character strings in the document not contained in a stop list, having at least a first predetermined number of characters, and containing at least a second predetermined number of strokes, said stop list stored in the memory of the computer;
b) using the computer, automatically determining a frequency of occurrence of characters in the document not contained in said stop list and containing at least said second predetermined number of strokes;
c) using the computer, automatically forming a seed list comprised of a third predetermined number of the most frequently occurring characters and character strings determined in steps (a) and (b), said seed list stored in the memory of the computer;
d) using the computer, automatically forming a summary of the document comprised of all sentences in the document containing at least two members of said seed list and surrounding sentences, said summary stored in the memory of the computer; and
e) using the computer, automatically repeating steps (a)-(d) on said summary until a length of said summary is not greater than a predetermined length, each time steps (a)-(d) are repeated, adding the members on said seed list to said stop list and reducing values of said first and second predetermined numbers.
43. A computer apparatus for automatically processing a document containing text represented by characters, comprising:
input means for automatically inputting a document into a memory of the computer apparatus to produce document data;
a processor coupled to said memory and including:
frequency determining means, receiving said document data from said memory, for automatically determining a frequency of occurrence of expressions in the document not contained in a stop list and having at least a first predetermined level of complexity, said frequency determining means outputting expression frequency data, said stop list stored in said memory;
seed list defining means, receiving said expression frequency data from said frequency determining means, for automatically defining a seed list comprised of a second predetermined number of the most frequently occurring expressions in the document, said seed list stored in said memory;
identifying means for automatically identifying portions of the document data containing at least two members of said seed list;
summarizing means for automatically forming a summary by combining said portions identified by said identifying means, said summary stored in said memory;
length determining means for automatically determining whether a length of said summary is not greater than a predetermined length; and
control means for automatically outputting said summary as a document summary when said length determining means determines said summary to be not greater than said predetermined length, otherwise automatically inputting said summary as a document to said input means, adding members of said seed list to said stop list, and reducing said first predetermined level of complexity so that said document data is iteratively processed until a document summary is produced having a length not greater than said predetermined length.
44. The apparatus of claim 43, wherein said input means produces said document data as decoded text data.
45. The apparatus of claim 43, wherein said expressions are represented in the document as at least one character, and said frequency determining means automatically determines whether said expressions have said first predetermined level of complexity by determining a number of strokes in said expressions.
46. The apparatus of claim 43, wherein said expressions are represented in the document as character strings, and said frequency determining means automatically determines whether said expressions have said first predetermined level of complexity by determining a number of characters in said expressions.
47. The apparatus of claim 43, wherein said expressions are represented in the document as character strings, and said frequency determining means automatically determines whether said expressions have said first predetermined level of complexity by determining a number of strokes in said expressions.
48. The apparatus of claim 43, wherein said expressions are represented in the document as words, and said frequency determining means automatically determines whether said expressions have said first predetermined level of complexity by determining a length of said words.
49. The apparatus of claim 48, wherein said frequency determining means automatically determines the length of said words by determining a number of characters in said words.
50. The apparatus of claim 43, wherein said identifying means automatically identifies sentences containing at least two of said members of said seed list.
51. The apparatus of claim 50, wherein each of said portions includes a sentence containing at least two of said members of said seed list and immediately preceding and following sentences located in a same paragraph as said sentence containing at least two of said members of said seed list.
52. The apparatus of claim 43, wherein said processor further includes means for automatically predefining members of said stop list before a document is input to said input means.
53. The apparatus of claim 43, wherein said summarizing means forms said summary by extracting said portions from said document and constructing said summary from said extracted portions while maintaining said extracted portions in a same order in said summary as in the document.
54. The apparatus of claim 43, further comprising a display screen for displaying said output document summary.
55. The apparatus of claim 43, further comprising a printer for printing said output document summary.
US08085385 1993-07-02 1993-07-02 Method and apparatus for summarizing documents according to theme Expired - Lifetime US5384703A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US08085385 US5384703A (en) 1993-07-02 1993-07-02 Method and apparatus for summarizing documents according to theme

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08085385 US5384703A (en) 1993-07-02 1993-07-02 Method and apparatus for summarizing documents according to theme
JP14271794A JP3839069B2 (en) 1993-07-02 1994-06-24 Method and apparatus for summarizing a document

Publications (1)

Publication Number Publication Date
US5384703A true US5384703A (en) 1995-01-24

Family

ID=22191283

Family Applications (1)

Application Number Title Priority Date Filing Date
US08085385 Expired - Lifetime US5384703A (en) 1993-07-02 1993-07-02 Method and apparatus for summarizing documents according to theme

Country Status (2)

Country Link
US (1) US5384703A (en)
JP (1) JP3839069B2 (en)

Cited By (154)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5537586A (en) * 1992-04-30 1996-07-16 Individual, Inc. Enhanced apparatus and methods for retrieving and selecting profiled textural information records from a database of defined category structures
EP0737927A2 (en) * 1995-04-14 1996-10-16 Xerox Corporation Automatic method of generating thematic summaries
EP0751470A1 (en) * 1995-06-28 1997-01-02 Xerox Corporation Automatic method of generating feature probabilities for automatic extracting summarization
EP0751469A1 (en) * 1995-06-28 1997-01-02 Xerox Corporation Automatic method of extracting summarization using feature probabilities
US5642520A (en) * 1993-12-07 1997-06-24 Nippon Telegraph And Telephone Corporation Method and apparatus for recognizing topic structure of language data
US5694523A (en) * 1995-05-31 1997-12-02 Oracle Corporation Content processing system for discourse
US5708822A (en) * 1995-05-31 1998-01-13 Oracle Corporation Methods and apparatus for thematic parsing of discourse
US5761665A (en) * 1995-10-31 1998-06-02 Pitney Bowes Inc. Method of automatic database field identification for postal coding
WO1998025216A1 (en) * 1996-12-05 1998-06-11 Interval Research Corporation Indirect manipulation of data using temporally related data, with particular application to manipulation of audio or audiovisual data
US5838323A (en) * 1995-09-29 1998-11-17 Apple Computer, Inc. Document summary computer system user interface
US5937422A (en) * 1997-04-15 1999-08-10 The United States Of America As Represented By The National Security Agency Automatically generating a topic description for text and searching and sorting text by topic using the same
US5960383A (en) * 1997-02-25 1999-09-28 Digital Equipment Corporation Extraction of key sections from texts using automatic indexing techniques
US5963969A (en) * 1997-05-08 1999-10-05 William A. Tidwell Document abstraction system and method thereof
US5983171A (en) * 1996-01-11 1999-11-09 Hitachi, Ltd. Auto-index method for electronic document files and recording medium utilizing a word/phrase analytical program
US5999925A (en) * 1997-07-25 1999-12-07 Claritech Corporation Information retrieval based on use of sub-documents
WO2000019334A1 (en) * 1998-09-28 2000-04-06 Prompt Software, Inc. Language independent phrase extraction
US6055544A (en) * 1996-03-15 2000-04-25 Inso Providence Corporation Generation of chunks of a long document for an electronic book system
US6064952A (en) * 1994-11-18 2000-05-16 Matsushita Electric Industrial Co., Ltd. Information abstracting method, information abstracting apparatus, and weighting method
WO2000041096A1 (en) * 1999-01-07 2000-07-13 Justsystem Corporation Method for producing summaries of text document
US6098034A (en) * 1996-03-18 2000-08-01 Expert Ease Development, Ltd. Method for standardizing phrasing in a document
US6101511A (en) * 1991-07-19 2000-08-08 Enigma Information Systems Ltd. Data processing system and method for generating a representation for and random access rendering of electronic documents
WO2000049517A2 (en) * 1999-02-19 2000-08-24 The Trustees Of Columbia University In The City Of New York Multi-document summarization system and method
US6112201A (en) * 1995-08-29 2000-08-29 Oracle Corporation Virtual bookshelf
US6167409A (en) * 1996-03-01 2000-12-26 Enigma Information Systems Ltd. Computer system and method for customizing context information sent with document fragments across a computer network
US6185592B1 (en) * 1997-11-18 2001-02-06 Apple Computer, Inc. Summarizing text documents by resolving co-referentiality among actors or objects around which a story unfolds
US6199034B1 (en) 1995-05-31 2001-03-06 Oracle Corporation Methods and apparatus for determining theme for discourse
US6246996B1 (en) 1994-09-16 2001-06-12 Messagemedia, Inc. Computerized system for facilitating transactions between parties on the internet using e-mail
US6289350B1 (en) 1999-08-20 2001-09-11 Newsgems Llc System and method for structured news release generation and distribution
US6289304B1 (en) * 1998-03-23 2001-09-11 Xerox Corporation Text summarization using part-of-speech
US6369811B1 (en) 1998-09-09 2002-04-09 Ricoh Company Limited Automatic adaptive document help for paper documents
US6370535B1 (en) 1999-08-20 2002-04-09 Newsgems Llc System and method for structured news release generation and distribution
US6374209B1 (en) * 1998-03-19 2002-04-16 Sharp Kabushiki Kaisha Text structure analyzing apparatus, abstracting apparatus, and program recording medium
US20020052730A1 (en) * 2000-09-25 2002-05-02 Yoshio Nakao Apparatus for reading a plurality of documents and a method thereof
US20020052783A1 (en) * 2000-06-26 2002-05-02 Turek David G. Method and apparatus for establishing a customized electronic site
US20020067380A1 (en) * 1999-03-23 2002-06-06 Jamey Graham Method and system for organizing document information
WO2002046960A2 (en) * 2000-11-23 2002-06-13 Goren Gordon Method and system for creating meaningful summaries from interrelated sets of information units
US6418434B1 (en) * 1999-06-25 2002-07-09 International Business Machines Corporation Two stage automated electronic messaging system
US20020128818A1 (en) * 1996-12-02 2002-09-12 Ho Chi Fai Method and system to answer a natural-language question
US6457026B1 (en) 1997-12-22 2002-09-24 Ricoh Company, Ltd. System to facilitate reading a document
US20020138493A1 (en) * 1999-08-20 2002-09-26 Shapiro Eileen C. System and method for structured news release generation and distribution
US20020133955A1 (en) * 2001-03-26 2002-09-26 Makita Corporation Circular saw with improved corner cutting
US6470307B1 (en) * 1997-06-23 2002-10-22 National Research Council Of Canada Method and apparatus for automatically identifying keywords within a document
US20020156810A1 (en) * 2001-04-19 2002-10-24 International Business Machines Corporation Method and system for identifying relationships between text documents and structured variables pertaining to the text documents
US20020156618A1 (en) * 2001-02-12 2002-10-24 Sharad Mathur Compressing messages on a per semantic component basis while maintaining a degree of human readability
US20020161770A1 (en) * 1999-08-20 2002-10-31 Shapiro Eileen C. System and method for structured news release generation and distribution
US20020169872A1 (en) * 2001-05-14 2002-11-14 Hiroshi Nomiyama Method for arranging information, information processing apparatus, storage media and program tranmission apparatus
US20020174149A1 (en) * 2001-04-27 2002-11-21 Conroy John M. Method of summarizing text by sentence extraction
US20030033137A1 (en) * 2001-05-24 2003-02-13 International Business Machines Corporation Method and system for translation management of source language text phrases
US6530235B2 (en) * 2000-11-01 2003-03-11 Edward Mayer Halimi Self-chilling portable beverage container assembly, and method
US6533822B2 (en) * 1998-01-30 2003-03-18 Xerox Corporation Creating summaries along with indicators, and automatically positioned tabs
US6546406B1 (en) 1995-11-03 2003-04-08 Enigma Information Systems Ltd. Client-server computer system for large document retrieval on networked computer system
US20030083862A1 (en) * 2001-10-30 2003-05-01 Zengjian Hu Method for extracting name entities and jargon terms using a suffix tree data structure
US20030095782A1 (en) * 2001-11-20 2003-05-22 Gordonomics Ltd. System and method for detection and analysis of video recordings
US6581057B1 (en) 2000-05-09 2003-06-17 Justsystem Corporation Method and apparatus for rapidly producing document summaries and document browsing aids
US6582475B2 (en) 1998-09-09 2003-06-24 Ricoh Company Limited Automatic adaptive document printing help system
US20030144617A1 (en) * 2002-01-25 2003-07-31 Oliver Scheib Massage device
US20030159107A1 (en) * 2002-02-21 2003-08-21 Xerox Corporation Methods and systems for incrementally changing text representation
US20030173937A1 (en) * 2002-03-15 2003-09-18 Tdk Corporation Switching power supply control circuit and switching power supply using same
US20030179236A1 (en) * 2002-02-21 2003-09-25 Xerox Corporation Methods and systems for interactive classification of objects
US6638317B2 (en) * 1998-03-20 2003-10-28 Fujitsu Limited Apparatus and method for generating digest according to hierarchical structure of topic
US6647534B1 (en) 1999-06-30 2003-11-11 Ricoh Company Limited Method and system for organizing document information in a non-directed arrangement of documents
US20030224341A1 (en) * 1996-12-02 2003-12-04 Ho Chi Fai Learning method and system based on questioning
US20040034835A1 (en) * 2001-10-19 2004-02-19 Xerox Corporation Method and apparatus for generating a summary from a document image
US20040034832A1 (en) * 2001-10-19 2004-02-19 Xerox Corporation Method and apparatus for foward annotating documents
US6714944B1 (en) 1999-11-30 2004-03-30 Verivita Llc System and method for authenticating and registering personal background data
US20040090462A1 (en) * 1997-12-22 2004-05-13 Ricoh Company, Ltd. Multimedia visualization and integration environment
US20040098671A1 (en) * 2002-02-21 2004-05-20 Ricoh Company, Ltd. Interface for printing multimedia information
US20040095376A1 (en) * 2002-02-21 2004-05-20 Ricoh Company, Ltd. Techniques for displaying information stored in multiple multimedia documents
US6742163B1 (en) * 1997-01-31 2004-05-25 Kabushiki Kaisha Toshiba Displaying multiple document abstracts in a single hyperlinked abstract, and their modified source documents
US20040117725A1 (en) * 2002-12-16 2004-06-17 Chen Francine R. Systems and methods for sentence based interactive topic-based text summarization
US20040117740A1 (en) * 2002-12-16 2004-06-17 Chen Francine R. Systems and methods for displaying interactive topic-based text summaries
US20040122657A1 (en) * 2002-12-16 2004-06-24 Brants Thorsten H. Systems and methods for interactive topic-based text summarization
US20040193571A1 (en) * 2003-03-31 2004-09-30 Ricoh Company, Ltd. Multimedia document sharing method and apparatus
US20050003337A1 (en) * 2003-07-02 2005-01-06 Berman Dennis R. Lock-In Training system
US20050010409A1 (en) * 2001-11-19 2005-01-13 Hull Jonathan J. Printable representations for time-based media
US20050022122A1 (en) * 2003-03-31 2005-01-27 John Barrus Document collection manipulation
US20050050344A1 (en) * 2003-08-11 2005-03-03 Hull Jonathan J. Multimedia output device having embedded encryption functionality
US20050055212A1 (en) * 1999-06-30 2005-03-10 Katashi Nagao Electronic document processing apparatus
US20050060141A1 (en) * 2002-12-12 2005-03-17 Masaharu Suzuki Information processing apparatus, information processing method and information processing program
US6880171B1 (en) 1996-12-05 2005-04-12 Interval Research Corporation Browser for use in navigating a body of information, with particular application to browsing information represented by audiovisual data
WO2005048120A1 (en) * 2003-11-07 2005-05-26 Motorola Inc. Text summarization
US20050119873A1 (en) * 1998-09-28 2005-06-02 Intesoft Systems Llc Method and apparatus for generating a language independent document abstract
US6904564B1 (en) 2002-01-14 2005-06-07 The United States Of America As Represented By The National Security Agency Method of summarizing text using just the text
US20050149849A1 (en) * 2001-11-19 2005-07-07 Ricoh Company, Ltd. Paper interface for simulation environments
US20050144908A1 (en) * 2004-01-02 2005-07-07 Cvc Technologies, Inc. Apparatus for tightening and loosening caps on containers
US20050149316A1 (en) * 2003-03-14 2005-07-07 Fujitsu Limited Translation support device
US20050162686A1 (en) * 2003-03-31 2005-07-28 Barrus John W. Check boxes for identifying and processing stored documents
US6941513B2 (en) 2000-06-15 2005-09-06 Cognisphere, Inc. System and method for text structuring and text generation
US20050216919A1 (en) * 1998-09-09 2005-09-29 Ricoh Company, Ltd. Device for generating a multimedia paper document
US20050216838A1 (en) * 2001-11-19 2005-09-29 Ricoh Company, Ltd. Techniques for generating a static representation for time-based media information
US20050216851A1 (en) * 1998-09-09 2005-09-29 Ricoh Company, Ltd. Techniques for annotating multimedia information
US20050216852A1 (en) * 1998-09-09 2005-09-29 Ricoh Company, Ltd. Techniques for generating a coversheet for a paper-based interface for multimedia information
US20050223322A1 (en) * 2001-11-19 2005-10-06 Ricoh Company, Ltd. Paper-based interface for specifying ranges
US20050221267A1 (en) * 2004-03-31 2005-10-06 Berman Dennis R Methods of selecting Lock-In Training courses and sessions
US6963830B1 (en) * 1999-07-19 2005-11-08 Fujitsu Limited Apparatus and method for generating a summary according to hierarchical structure of topic
US20050251743A1 (en) * 2004-05-10 2005-11-10 Fuji Xerox Co., Ltd. Learning apparatus, program therefor and storage medium
US20050262214A1 (en) * 2004-04-27 2005-11-24 Amit Bagga Method and apparatus for summarizing one or more text messages using indicative summaries
US20060031885A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of music-related broadcasted or streamed multimedia content
US20060031916A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of broadcasted or streamed multimedia content
US20060031879A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of news-related broadcasted or streamed multimedia content
US20060059442A1 (en) * 1995-09-29 2006-03-16 Bornstein Jeremy J Interactive document summarization
US20060085743A1 (en) * 2004-10-18 2006-04-20 Microsoft Corporation Semantic thumbnails
US20060116957A1 (en) * 2000-03-17 2006-06-01 Jason May Method and apparatus for facilitating online payment transactions in a network-based transaction facility
US7074128B2 (en) 2001-08-03 2006-07-11 Drb Lit Ltd. Method and system for enhancing memorization by using a mnemonic display
US7124093B1 (en) 1997-12-22 2006-10-17 Ricoh Company, Ltd. Method, system and computer code for content based web advertising
US20060247599A1 (en) * 2005-04-29 2006-11-02 Kimberly-Clark Worldwide, Inc. Garment having an outer shell that freely moves in relation to an absorbent assembly therein
US20060262995A1 (en) * 2003-03-31 2006-11-23 John Barrus Action stickers for identifying and processing stored documents
US7149957B2 (en) 2001-11-19 2006-12-12 Ricoh Company, Ltd. Techniques for retrieving multimedia information using a paper-based interface
USRE39435E1 (en) 2000-10-17 2006-12-19 Drb Lit Ltd. Learning system with learner-constructed response based methodology
US7158983B2 (en) 2002-09-23 2007-01-02 Battelle Memorial Institute Text analysis technique
US7162413B1 (en) 1999-07-09 2007-01-09 International Business Machines Corporation Rule induction for summarizing documents in a classified document collection
US20070050696A1 (en) * 2003-03-31 2007-03-01 Piersol Kurt W Physical key for accessing a securely stored digital document
US20070073618A1 (en) * 2005-09-29 2007-03-29 Ebay Inc. Release of funds based on criteria
US7200808B1 (en) 1998-04-02 2007-04-03 Sony Corporation Electronic document processor
US7228507B2 (en) 2002-02-21 2007-06-05 Xerox Corporation Methods and systems for navigating a workspace
US7228492B1 (en) 1999-07-06 2007-06-05 Ricoh Company, Ltd. 2D graph displaying document locations of user-specified concept of interest
US7257589B1 (en) 1997-12-22 2007-08-14 Ricoh Company, Ltd. Techniques for targeting information to users
US7263659B2 (en) 1998-09-09 2007-08-28 Ricoh Company, Ltd. Paper-based interface for multimedia information
US20080028292A1 (en) * 1997-12-22 2008-01-31 Ricoh Company, Ltd. Techniques to facilitate reading of a document
US7366711B1 (en) 1999-02-19 2008-04-29 The Trustees Of Columbia University In The City Of New York Multi-document summarization system and method
US20080235576A1 (en) * 1999-12-23 2008-09-25 International Business Machines Corporation Method and system for automatic computation creativity and specifically for story generation
US20080243820A1 (en) * 2007-03-27 2008-10-02 Walter Chang Semantic analysis documents to rank terms
US20080270119A1 (en) * 2007-04-30 2008-10-30 Microsoft Corporation Generating sentence variations for automatic summarization
US20080282159A1 (en) * 2007-05-11 2008-11-13 Microsoft Corporation Summarization of attached, linked or related materials
US20080281927A1 (en) * 2007-05-11 2008-11-13 Microsoft Corporation Summarization tool and method for a dialogue sequence
US20080320384A1 (en) * 2007-06-25 2008-12-25 Ramesh Nagarajan Automated addition of images to text
US7480446B2 (en) 1996-12-05 2009-01-20 Vulcan Patents Llc Variable rate video playback with synchronized audio
US7487462B2 (en) 2002-02-21 2009-02-03 Xerox Corporation Methods and systems for indicating invisible contents of workspace
US7509569B2 (en) 2003-03-31 2009-03-24 Ricoh Co., Ltd. Action stickers for nested collections
US7549114B2 (en) 2002-02-21 2009-06-16 Xerox Corporation Methods and systems for incrementally changing text representation
US7565681B2 (en) 1999-10-08 2009-07-21 Vulcan Patents Llc System and method for the broadcast dissemination of time-ordered data
US20090210402A1 (en) * 2008-02-18 2009-08-20 Samsung Electronics Co. Ltd. System and method for contextual association discovery to conceptualize user query
US7610546B1 (en) 1999-08-02 2009-10-27 Sony Corporation Document processing apparatus having capability of controlling video data
US20100057710A1 (en) * 2008-08-28 2010-03-04 Yahoo! Inc Generation of search result abstracts
US7703002B2 (en) 2003-03-31 2010-04-20 Ricoh Company, Ltd. Method and apparatus for composing multimedia documents
US7779355B1 (en) 2004-03-30 2010-08-17 Ricoh Company, Ltd. Techniques for using paper documents as media templates
US20100235331A1 (en) * 2009-03-16 2010-09-16 Silich Bert A User-determinable method and system for manipulating and displaying textual and graphical information
US7849475B2 (en) 1995-03-07 2010-12-07 Interval Licensing Llc System and method for selective recording of information
US7861169B2 (en) 2001-11-19 2010-12-28 Ricoh Co. Ltd. Multimedia print driver dialog interfaces
US7954056B2 (en) 1997-12-22 2011-05-31 Ricoh Company, Ltd. Television-based visualization and navigation interface
US20120166940A1 (en) * 2010-12-28 2012-06-28 Elwha LLC, a limited liability company of the State of Delaware Multi-view graphical user interface for editing a base document with highlighting feature
US8239358B1 (en) * 2007-02-06 2012-08-07 Dmitri Soubbotin System, method, and user interface for a search engine based on multi-document summarization
US8255325B2 (en) 2000-03-17 2012-08-28 Ebay Inc. Method and apparatus for facilitating online payment transactions in a network-based transaction facility using multiple payment instruments
US8280888B1 (en) * 2012-05-04 2012-10-02 Pearl.com LLC Method and apparatus for creation of web document titles optimized for search engines
US20130030792A1 (en) * 2011-07-26 2013-01-31 International Business Machines Corporation Customization of a Natural Language Processing Engine
US8429244B2 (en) 2000-01-28 2013-04-23 Interval Licensing Llc Alerting users to items of current interest
US20130151944A1 (en) * 2011-12-13 2013-06-13 Microsoft Corporation Highlighting of tappable web page elements
US8488916B2 (en) * 2011-07-22 2013-07-16 David S Terman Knowledge acquisition nexus for facilitating concept capture and promoting time on task
US8539344B2 (en) 2001-11-19 2013-09-17 Ricoh Company, Ltd. Paper-based interface for multimedia information stored by multiple multimedia documents
US9275038B2 (en) 2012-05-04 2016-03-01 Pearl.com LLC Method and apparatus for identifying customer service and duplicate questions in an online consultation system
US9442928B2 (en) 2011-09-07 2016-09-13 Venio Inc. System, method and computer program product for automatic topic identification using a hypertext corpus
US9442930B2 (en) 2011-09-07 2016-09-13 Venio Inc. System, method and computer program product for automatic topic identification using a hypertext corpus
US9501580B2 (en) 2012-05-04 2016-11-22 Pearl.com LLC Method and apparatus for automated selection of interesting content for presentation to first time visitors of a website
US9646079B2 (en) 2012-05-04 2017-05-09 Pearl.com LLC Method and apparatus for identifiying similar questions in a consultation system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4553860A (en) * 1982-09-10 1985-11-19 Brother Kogyo Kabushiki Kaisha Text processing method and apparatus
US4965763A (en) * 1987-03-03 1990-10-23 International Business Machines Corporation Computer method for automatic extraction of commonly specified information from business correspondence
US5077668A (en) * 1988-09-30 1991-12-31 Kabushiki Kaisha Toshiba Method and apparatus for producing an abstract of a document
US5257186A (en) * 1990-05-21 1993-10-26 Kabushiki Kaisha Toshiba Digital computing apparatus for preparing document text

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4553860A (en) * 1982-09-10 1985-11-19 Brother Kogyo Kabushiki Kaisha Text processing method and apparatus
US4965763A (en) * 1987-03-03 1990-10-23 International Business Machines Corporation Computer method for automatic extraction of commonly specified information from business correspondence
US5077668A (en) * 1988-09-30 1991-12-31 Kabushiki Kaisha Toshiba Method and apparatus for producing an abstract of a document
US5257186A (en) * 1990-05-21 1993-10-26 Kabushiki Kaisha Toshiba Digital computing apparatus for preparing document text

Non-Patent Citations (9)

* Cited by examiner, † Cited by third party
Title
Jones, Richard L., 1990, Aida The Artificially Intelligent Document Analyzer. Computer Power Group, Canberra, Australia. *
Luhn, H. P. 1958 The Automatic creation of literature abstracts IBM Foundation of Research & Development pp. 159 165. *
Luhn, H. P. 1958 The Automatic creation of literature abstracts IBM Foundation of Research & Development pp. 159-165.
Luhn, H. P. 1958, The Automatic Creation of Literature Abstracts. IBM Foundation of Research and Development, 2(4): 314 319. *
Luhn, H. P. 1958, The Automatic Creation of Literature Abstracts. IBM Foundation of Research and Development, 2(4): 314-319.
Paice et al., "The Identification of Important Concepts in Highly Structured Technical Papers"; ACM-SIGIR'93-Jun. 1993/ Pittsburgh, Pa. USA; pp. 69-78.
Paice et al., The Identification of Important Concepts in Highly Structured Technical Papers ; ACM SIGIR 93 Jun. 1993/ Pittsburgh, Pa. USA; pp. 69 78. *
Salton, G. and M. F. McGill, 1983. Introduction to Modern Information Retrieval, New York: McGraw Hill. *
Salton, G. and M. F. McGill, 1983. Introduction to Modern Information Retrieval, New York: McGraw-Hill.

Cited By (267)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6101511A (en) * 1991-07-19 2000-08-08 Enigma Information Systems Ltd. Data processing system and method for generating a representation for and random access rendering of electronic documents
US6101512A (en) * 1991-07-19 2000-08-08 Enigma Information Systems Ltd. Data processing system and method for generating a representation for and random access rendering of electronic documents
US6105044A (en) * 1991-07-19 2000-08-15 Enigma Information Systems Ltd. Data processing system and method for generating a representation for and random access rendering of electronic documents
US5537586A (en) * 1992-04-30 1996-07-16 Individual, Inc. Enhanced apparatus and methods for retrieving and selecting profiled textural information records from a database of defined category structures
US5642520A (en) * 1993-12-07 1997-06-24 Nippon Telegraph And Telephone Corporation Method and apparatus for recognizing topic structure of language data
US6246996B1 (en) 1994-09-16 2001-06-12 Messagemedia, Inc. Computerized system for facilitating transactions between parties on the internet using e-mail
US6502065B2 (en) * 1994-11-18 2002-12-31 Matsushita Electric Industrial Co., Ltd. Teletext broadcast receiving apparatus using keyword extraction and weighting
US6240378B1 (en) 1994-11-18 2001-05-29 Matsushita Electric Industrial Co., Ltd. Weighting method for use in information extraction and abstracting, based on the frequency of occurrence of keywords and similarity calculations
US6064952A (en) * 1994-11-18 2000-05-16 Matsushita Electric Industrial Co., Ltd. Information abstracting method, information abstracting apparatus, and weighting method
US20110055861A1 (en) * 1995-03-07 2011-03-03 Michele Mae Covell System and method for selective recording of information
US7849475B2 (en) 1995-03-07 2010-12-07 Interval Licensing Llc System and method for selective recording of information
US8584158B2 (en) 1995-03-07 2013-11-12 Interval Licensing Llc System and method for selective recording of information
EP0737927A3 (en) * 1995-04-14 1998-11-18 Xerox Corporation Automatic method of generating thematic summaries
EP0737927A2 (en) * 1995-04-14 1996-10-16 Xerox Corporation Automatic method of generating thematic summaries
US5694523A (en) * 1995-05-31 1997-12-02 Oracle Corporation Content processing system for discourse
US6199034B1 (en) 1995-05-31 2001-03-06 Oracle Corporation Methods and apparatus for determining theme for discourse
US5708822A (en) * 1995-05-31 1998-01-13 Oracle Corporation Methods and apparatus for thematic parsing of discourse
US5778397A (en) * 1995-06-28 1998-07-07 Xerox Corporation Automatic method of generating feature probabilities for automatic extracting summarization
EP0751469A1 (en) * 1995-06-28 1997-01-02 Xerox Corporation Automatic method of extracting summarization using feature probabilities
EP0751470A1 (en) * 1995-06-28 1997-01-02 Xerox Corporation Automatic method of generating feature probabilities for automatic extracting summarization
US5918240A (en) * 1995-06-28 1999-06-29 Xerox Corporation Automatic method of extracting summarization using feature probabilities
US6112201A (en) * 1995-08-29 2000-08-29 Oracle Corporation Virtual bookshelf
US20060265666A1 (en) * 1995-09-29 2006-11-23 Bornstein Jeremy J Interactive document summarization
US7886235B2 (en) 1995-09-29 2011-02-08 Apple Inc. Interactive document summarization
US20060059442A1 (en) * 1995-09-29 2006-03-16 Bornstein Jeremy J Interactive document summarization
US5838323A (en) * 1995-09-29 1998-11-17 Apple Computer, Inc. Document summary computer system user interface
US7882450B2 (en) 1995-09-29 2011-02-01 Apple Inc. Interactive document summarization
US5761665A (en) * 1995-10-31 1998-06-02 Pitney Bowes Inc. Method of automatic database field identification for postal coding
US6546406B1 (en) 1995-11-03 2003-04-08 Enigma Information Systems Ltd. Client-server computer system for large document retrieval on networked computer system
US5983171A (en) * 1996-01-11 1999-11-09 Hitachi, Ltd. Auto-index method for electronic document files and recording medium utilizing a word/phrase analytical program
US6167409A (en) * 1996-03-01 2000-12-26 Enigma Information Systems Ltd. Computer system and method for customizing context information sent with document fragments across a computer network
US6055544A (en) * 1996-03-15 2000-04-25 Inso Providence Corporation Generation of chunks of a long document for an electronic book system
US6098034A (en) * 1996-03-18 2000-08-01 Expert Ease Development, Ltd. Method for standardizing phrasing in a document
US20020128818A1 (en) * 1996-12-02 2002-09-12 Ho Chi Fai Method and system to answer a natural-language question
US20040110120A1 (en) * 1996-12-02 2004-06-10 Mindfabric, Inc. Learning method and system based on questioning
US20030224341A1 (en) * 1996-12-02 2003-12-04 Ho Chi Fai Learning method and system based on questioning
US6865370B2 (en) 1996-12-02 2005-03-08 Mindfabric, Inc. Learning method and system based on questioning
WO1998025216A1 (en) * 1996-12-05 1998-06-11 Interval Research Corporation Indirect manipulation of data using temporally related data, with particular application to manipulation of audio or audiovisual data
US6880171B1 (en) 1996-12-05 2005-04-12 Interval Research Corporation Browser for use in navigating a body of information, with particular application to browsing information represented by audiovisual data
US8176515B2 (en) 1996-12-05 2012-05-08 Interval Licensing Llc Browser for use in navigating a body of information, with particular application to browsing information represented by audiovisual data
US20070204319A1 (en) * 1996-12-05 2007-08-30 Subutai Ahmad Browser for use in navigating a body of information, with particular application to browsing information represented by audiovisual data
US7480446B2 (en) 1996-12-05 2009-01-20 Vulcan Patents Llc Variable rate video playback with synchronized audio
US6172675B1 (en) 1996-12-05 2001-01-09 Interval Research Corporation Indirect manipulation of data using temporally related data, with particular application to manipulation of audio or audiovisual data
US8238722B2 (en) 1996-12-05 2012-08-07 Interval Licensing Llc Variable rate video playback with synchronized audio
US6742163B1 (en) * 1997-01-31 2004-05-25 Kabushiki Kaisha Toshiba Displaying multiple document abstracts in a single hyperlinked abstract, and their modified source documents
US7065708B2 (en) 1997-01-31 2006-06-20 Kabushiki Kaisha Toshiba Displaying multiple ranked document abstracts in a single hyperlinked abstract, and their modified source documents
US5960383A (en) * 1997-02-25 1999-09-28 Digital Equipment Corporation Extraction of key sections from texts using automatic indexing techniques
US5937422A (en) * 1997-04-15 1999-08-10 The United States Of America As Represented By The National Security Agency Automatically generating a topic description for text and searching and sorting text by topic using the same
US5963969A (en) * 1997-05-08 1999-10-05 William A. Tidwell Document abstraction system and method thereof
US6470307B1 (en) * 1997-06-23 2002-10-22 National Research Council Of Canada Method and apparatus for automatically identifying keywords within a document
US5999925A (en) * 1997-07-25 1999-12-07 Claritech Corporation Information retrieval based on use of sub-documents
US6115706A (en) * 1997-07-25 2000-09-05 Claritech Corporation Information retrieval based on use of subdocuments
US6377947B1 (en) 1997-07-25 2002-04-23 Claritech Corporation Information retrieval based on using and locating subdocuments
US6185592B1 (en) * 1997-11-18 2001-02-06 Apple Computer, Inc. Summarizing text documents by resolving co-referentiality among actors or objects around which a story unfolds
US8739040B2 (en) 1997-12-22 2014-05-27 Ricoh Company, Ltd. Multimedia visualization and integration environment
US7596755B2 (en) 1997-12-22 2009-09-29 Ricoh Company, Ltd. Multimedia visualization and integration environment
US7257589B1 (en) 1997-12-22 2007-08-14 Ricoh Company, Ltd. Techniques for targeting information to users
US20040175036A1 (en) * 1997-12-22 2004-09-09 Ricoh Company, Ltd. Multimedia visualization and integration environment
US20040090462A1 (en) * 1997-12-22 2004-05-13 Ricoh Company, Ltd. Multimedia visualization and integration environment
US8438164B2 (en) 1997-12-22 2013-05-07 Ricoh Co., Ltd. Techniques for targeting information to users
US7124093B1 (en) 1997-12-22 2006-10-17 Ricoh Company, Ltd. Method, system and computer code for content based web advertising
US7395501B2 (en) 1997-12-22 2008-07-01 Ricoh Company, Ltd. Techniques for annotating portions of a document relevant to concepts of interest
US20030051214A1 (en) * 1997-12-22 2003-03-13 Ricoh Company, Ltd. Techniques for annotating portions of a document relevant to concepts of interest
US20080005102A1 (en) * 1997-12-22 2008-01-03 Ricoh Company, Ltd. Techniques for Targeting Information to Users
US20080028292A1 (en) * 1997-12-22 2008-01-31 Ricoh Company, Ltd. Techniques to facilitate reading of a document
US8620747B2 (en) 1997-12-22 2013-12-31 Ricoh Company, Ltd. Method, system and computer code for content based web advertising
US8995767B2 (en) 1997-12-22 2015-03-31 Ricoh Company, Ltd. Multimedia visualization and integration environment
US7954056B2 (en) 1997-12-22 2011-05-31 Ricoh Company, Ltd. Television-based visualization and navigation interface
US6457026B1 (en) 1997-12-22 2002-09-24 Ricoh Company, Ltd. System to facilitate reading a document
US20040103372A1 (en) * 1997-12-22 2004-05-27 Ricoh Company, Ltd. Multimedia visualization and integration environment
US6533822B2 (en) * 1998-01-30 2003-03-18 Xerox Corporation Creating summaries along with indicators, and automatically positioned tabs
US6374209B1 (en) * 1998-03-19 2002-04-16 Sharp Kabushiki Kaisha Text structure analyzing apparatus, abstracting apparatus, and program recording medium
US6638317B2 (en) * 1998-03-20 2003-10-28 Fujitsu Limited Apparatus and method for generating digest according to hierarchical structure of topic
US6289304B1 (en) * 1998-03-23 2001-09-11 Xerox Corporation Text summarization using part-of-speech
US7200808B1 (en) 1998-04-02 2007-04-03 Sony Corporation Electronic document processor
US7263659B2 (en) 1998-09-09 2007-08-28 Ricoh Company, Ltd. Paper-based interface for multimedia information
US7266782B2 (en) 1998-09-09 2007-09-04 Ricoh Company, Ltd. Techniques for generating a coversheet for a paper-based interface for multimedia information
US7096424B2 (en) 1998-09-09 2006-08-22 Ricoh Company, Ltd. Automatic adaptive document printing help system
US6369811B1 (en) 1998-09-09 2002-04-09 Ricoh Company Limited Automatic adaptive document help for paper documents
US7263671B2 (en) 1998-09-09 2007-08-28 Ricoh Company, Ltd. Techniques for annotating multimedia information
US20040083431A1 (en) * 1998-09-09 2004-04-29 Ricoh Company, Ltd A Japanese Corporation Automatic adaptive document printing help system
US20050216919A1 (en) * 1998-09-09 2005-09-29 Ricoh Company, Ltd. Device for generating a multimedia paper document
US8112709B2 (en) 1998-09-09 2012-02-07 Ricoh Co., Ltd. Automatic adaptive document printing help system
US20050216851A1 (en) * 1998-09-09 2005-09-29 Ricoh Company, Ltd. Techniques for annotating multimedia information
US20050216852A1 (en) * 1998-09-09 2005-09-29 Ricoh Company, Ltd. Techniques for generating a coversheet for a paper-based interface for multimedia information
US6582475B2 (en) 1998-09-09 2003-06-24 Ricoh Company Limited Automatic adaptive document printing help system
US7215436B2 (en) 1998-09-09 2007-05-08 Ricoh Company, Ltd. Device for generating a multimedia paper document
US20100305942A1 (en) * 1998-09-28 2010-12-02 Chaney Garnet R Method and apparatus for generating a language independent document abstract
WO2000019334A1 (en) * 1998-09-28 2000-04-06 Prompt Software, Inc. Language independent phrase extraction
US8005665B2 (en) 1998-09-28 2011-08-23 Schukhaus Group Gmbh, Llc Method and apparatus for generating a language independent document abstract
US7447626B2 (en) * 1998-09-28 2008-11-04 Udico Holdings Method and apparatus for generating a language independent document abstract
US20090182553A1 (en) * 1998-09-28 2009-07-16 Udico Holdings Method and apparatus for generating a language independent document abstract
US6104990A (en) * 1998-09-28 2000-08-15 Prompt Software, Inc. Language independent phrase extraction
US7792667B2 (en) 1998-09-28 2010-09-07 Chaney Garnet R Method and apparatus for generating a language independent document abstract
US20050119873A1 (en) * 1998-09-28 2005-06-02 Intesoft Systems Llc Method and apparatus for generating a language independent document abstract
WO2000041096A1 (en) * 1999-01-07 2000-07-13 Justsystem Corporation Method for producing summaries of text document
US6317708B1 (en) 1999-01-07 2001-11-13 Justsystem Corporation Method for producing summaries of text document
WO2000049517A2 (en) * 1999-02-19 2000-08-24 The Trustees Of Columbia University In The City Of New York Multi-document summarization system and method
US7366711B1 (en) 1999-02-19 2008-04-29 The Trustees Of Columbia University In The City Of New York Multi-document summarization system and method
WO2000049517A3 (en) * 1999-02-19 2000-11-30 Univ Columbia Multi-document summarization system and method
US7730423B2 (en) 1999-03-23 2010-06-01 Ricoh Company, Ltd. Method and system for organizing document information
US20020067380A1 (en) * 1999-03-23 2002-06-06 Jamey Graham Method and system for organizing document information
US6418434B1 (en) * 1999-06-25 2002-07-09 International Business Machines Corporation Two stage automated electronic messaging system
US6985864B2 (en) 1999-06-30 2006-01-10 Sony Corporation Electronic document processing apparatus and method for forming summary text and speech read-out
US20050055212A1 (en) * 1999-06-30 2005-03-10 Katashi Nagao Electronic document processing apparatus
US6647534B1 (en) 1999-06-30 2003-11-11 Ricoh Company Limited Method and system for organizing document information in a non-directed arrangement of documents
US8185813B2 (en) 1999-07-06 2012-05-22 Ricoh Company, Ltd. 2D graph displaying document locations of user-specified concept of interest
US7228492B1 (en) 1999-07-06 2007-06-05 Ricoh Company, Ltd. 2D graph displaying document locations of user-specified concept of interest
US20070180372A1 (en) * 1999-07-06 2007-08-02 Ricoh Company Limited 2d graph displaying document locations of user-specified concept of interest
US7162413B1 (en) 1999-07-09 2007-01-09 International Business Machines Corporation Rule induction for summarizing documents in a classified document collection
US6963830B1 (en) * 1999-07-19 2005-11-08 Fujitsu Limited Apparatus and method for generating a summary according to hierarchical structure of topic
US7610546B1 (en) 1999-08-02 2009-10-27 Sony Corporation Document processing apparatus having capability of controlling video data
US8214386B2 (en) 1999-08-20 2012-07-03 Newgems Llc System and method for structured news release generation and distribution
US20020161770A1 (en) * 1999-08-20 2002-10-31 Shapiro Eileen C. System and method for structured news release generation and distribution
US6289350B1 (en) 1999-08-20 2001-09-11 Newsgems Llc System and method for structured news release generation and distribution
US7035848B2 (en) 1999-08-20 2006-04-25 Newsgems Llc System and method for structured news release generation and distribution
US6370535B1 (en) 1999-08-20 2002-04-09 Newsgems Llc System and method for structured news release generation and distribution
US20020138493A1 (en) * 1999-08-20 2002-09-26 Shapiro Eileen C. System and method for structured news release generation and distribution
US8046818B2 (en) 1999-10-08 2011-10-25 Interval Licensing Llc System and method for the broadcast dissemination of time-ordered data
US20090199248A1 (en) * 1999-10-08 2009-08-06 Ngo J Thomas System and method for the broadcast dissemination of time-ordered data
US7565681B2 (en) 1999-10-08 2009-07-21 Vulcan Patents Llc System and method for the broadcast dissemination of time-ordered data
US8341688B2 (en) 1999-10-08 2012-12-25 Interval Licensing Llc System and method for the broadcast dissemination of time-ordered data
US8726331B2 (en) 1999-10-08 2014-05-13 Interval Licensing Llc System and method for the broadcast dissemination of time-ordered data
US8037539B2 (en) 1999-11-30 2011-10-11 Verivita Llc System and method for providing access to verified personal background data
US20040168080A1 (en) * 1999-11-30 2004-08-26 Shapiro Eileen C. System and method for providing access to verified personal background data
US6714944B1 (en) 1999-11-30 2004-03-30 Verivita Llc System and method for authenticating and registering personal background data
US20080235576A1 (en) * 1999-12-23 2008-09-25 International Business Machines Corporation Method and system for automatic computation creativity and specifically for story generation
US8429244B2 (en) 2000-01-28 2013-04-23 Interval Licensing Llc Alerting users to items of current interest
US9317560B2 (en) 2000-01-28 2016-04-19 Interval Licensing Llc Alerting users to items of current interest
US8255325B2 (en) 2000-03-17 2012-08-28 Ebay Inc. Method and apparatus for facilitating online payment transactions in a network-based transaction facility using multiple payment instruments
US20060116957A1 (en) * 2000-03-17 2006-06-01 Jason May Method and apparatus for facilitating online payment transactions in a network-based transaction facility
US7899712B2 (en) 2000-03-17 2011-03-01 Ebay Inc. Method and apparatus for facilitating online payment transactions in a network-based transaction facility
US6581057B1 (en) 2000-05-09 2003-06-17 Justsystem Corporation Method and apparatus for rapidly producing document summaries and document browsing aids
US6941513B2 (en) 2000-06-15 2005-09-06 Cognisphere, Inc. System and method for text structuring and text generation
US20020052783A1 (en) * 2000-06-26 2002-05-02 Turek David G. Method and apparatus for establishing a customized electronic site
US20020052730A1 (en) * 2000-09-25 2002-05-02 Yoshio Nakao Apparatus for reading a plurality of documents and a method thereof
US7813915B2 (en) * 2000-09-25 2010-10-12 Fujitsu Limited Apparatus for reading a plurality of documents and a method thereof
USRE39435E1 (en) 2000-10-17 2006-12-19 Drb Lit Ltd. Learning system with learner-constructed response based methodology
US6530235B2 (en) * 2000-11-01 2003-03-11 Edward Mayer Halimi Self-chilling portable beverage container assembly, and method
WO2002046960A2 (en) * 2000-11-23 2002-06-13 Goren Gordon Method and system for creating meaningful summaries from interrelated sets of information units
WO2002046960A3 (en) * 2000-11-23 2003-08-14 Goren Gordon Method and system for creating meaningful summaries from interrelated sets of information units
US20020156618A1 (en) * 2001-02-12 2002-10-24 Sharad Mathur Compressing messages on a per semantic component basis while maintaining a degree of human readability
US7010478B2 (en) * 2001-02-12 2006-03-07 Microsoft Corporation Compressing messages on a per semantic component basis while maintaining a degree of human readability
US20020133955A1 (en) * 2001-03-26 2002-09-26 Makita Corporation Circular saw with improved corner cutting
US20020156810A1 (en) * 2001-04-19 2002-10-24 International Business Machines Corporation Method and system for identifying relationships between text documents and structured variables pertaining to the text documents
US7155668B2 (en) 2001-04-19 2006-12-26 International Business Machines Corporation Method and system for identifying relationships between text documents and structured variables pertaining to the text documents
US7810029B2 (en) 2001-04-19 2010-10-05 International Business Machines Corporation Method and system for identifying relationships between text documents and structured variables pertaining to the text documents
US6990634B2 (en) 2001-04-27 2006-01-24 The United States Of America As Represented By The National Security Agency Method of summarizing text by sentence extraction
US20020174149A1 (en) * 2001-04-27 2002-11-21 Conroy John M. Method of summarizing text by sentence extraction
US20020169872A1 (en) * 2001-05-14 2002-11-14 Hiroshi Nomiyama Method for arranging information, information processing apparatus, storage media and program tranmission apparatus
US20030033137A1 (en) * 2001-05-24 2003-02-13 International Business Machines Corporation Method and system for translation management of source language text phrases
US7074128B2 (en) 2001-08-03 2006-07-11 Drb Lit Ltd. Method and system for enhancing memorization by using a mnemonic display
US20040034835A1 (en) * 2001-10-19 2004-02-19 Xerox Corporation Method and apparatus for generating a summary from a document image
US20040034832A1 (en) * 2001-10-19 2004-02-19 Xerox Corporation Method and apparatus for foward annotating documents
US7712028B2 (en) 2001-10-19 2010-05-04 Xerox Corporation Using annotations for summarizing a document image and itemizing the summary based on similar annotations
US7197449B2 (en) * 2001-10-30 2007-03-27 Intel Corporation Method for extracting name entities and jargon terms using a suffix tree data structure
US20030083862A1 (en) * 2001-10-30 2003-05-01 Zengjian Hu Method for extracting name entities and jargon terms using a suffix tree data structure
US20050010409A1 (en) * 2001-11-19 2005-01-13 Hull Jonathan J. Printable representations for time-based media
US7747655B2 (en) 2001-11-19 2010-06-29 Ricoh Co. Ltd. Printable representations for time-based media
US7788080B2 (en) 2001-11-19 2010-08-31 Ricoh Company, Ltd. Paper interface for simulation environments
US20050216838A1 (en) * 2001-11-19 2005-09-29 Ricoh Company, Ltd. Techniques for generating a static representation for time-based media information
US7861169B2 (en) 2001-11-19 2010-12-28 Ricoh Co. Ltd. Multimedia print driver dialog interfaces
US7149957B2 (en) 2001-11-19 2006-12-12 Ricoh Company, Ltd. Techniques for retrieving multimedia information using a paper-based interface
US20050149849A1 (en) * 2001-11-19 2005-07-07 Ricoh Company, Ltd. Paper interface for simulation environments
US8539344B2 (en) 2001-11-19 2013-09-17 Ricoh Company, Ltd. Paper-based interface for multimedia information stored by multiple multimedia documents
US7743347B2 (en) 2001-11-19 2010-06-22 Ricoh Company, Ltd. Paper-based interface for specifying ranges
US7703044B2 (en) 2001-11-19 2010-04-20 Ricoh Company, Ltd. Techniques for generating a static representation for time-based media information
US7979786B1 (en) 2001-11-19 2011-07-12 Ricoh Company, Ltd. Techniques for retrieving multimedia information using a paper-based interface
US20050223322A1 (en) * 2001-11-19 2005-10-06 Ricoh Company, Ltd. Paper-based interface for specifying ranges
US6928228B2 (en) * 2001-11-20 2005-08-09 Gordonomics Ltd. System and method for detection and analysis of video recordings
US20030095782A1 (en) * 2001-11-20 2003-05-22 Gordonomics Ltd. System and method for detection and analysis of video recordings
US6904564B1 (en) 2002-01-14 2005-06-07 The United States Of America As Represented By The National Security Agency Method of summarizing text using just the text
US20030144617A1 (en) * 2002-01-25 2003-07-31 Oliver Scheib Massage device
US20040095376A1 (en) * 2002-02-21 2004-05-20 Ricoh Company, Ltd. Techniques for displaying information stored in multiple multimedia documents
US7487462B2 (en) 2002-02-21 2009-02-03 Xerox Corporation Methods and systems for indicating invisible contents of workspace
US7495795B2 (en) 2002-02-21 2009-02-24 Ricoh Company, Ltd. Interface for printing multimedia information
US7650562B2 (en) 2002-02-21 2010-01-19 Xerox Corporation Methods and systems for incrementally changing text representation
US20040098671A1 (en) * 2002-02-21 2004-05-20 Ricoh Company, Ltd. Interface for printing multimedia information
US8635531B2 (en) 2002-02-21 2014-01-21 Ricoh Company, Ltd. Techniques for displaying information stored in multiple multimedia documents
US20030159107A1 (en) * 2002-02-21 2003-08-21 Xerox Corporation Methods and systems for incrementally changing text representation
US20030179236A1 (en) * 2002-02-21 2003-09-25 Xerox Corporation Methods and systems for interactive classification of objects
US8370761B2 (en) 2002-02-21 2013-02-05 Xerox Corporation Methods and systems for interactive classification of objects
US7228507B2 (en) 2002-02-21 2007-06-05 Xerox Corporation Methods and systems for navigating a workspace
US7549114B2 (en) 2002-02-21 2009-06-16 Xerox Corporation Methods and systems for incrementally changing text representation
US20030173937A1 (en) * 2002-03-15 2003-09-18 Tdk Corporation Switching power supply control circuit and switching power supply using same
US7158983B2 (en) 2002-09-23 2007-01-02 Battelle Memorial Institute Text analysis technique
US7398202B2 (en) * 2002-12-12 2008-07-08 Honda Motor Co., Ltd. Information processing apparatus, information processing method and information processing program
US20050060141A1 (en) * 2002-12-12 2005-03-17 Masaharu Suzuki Information processing apparatus, information processing method and information processing program
US7117437B2 (en) 2002-12-16 2006-10-03 Palo Alto Research Center Incorporated Systems and methods for displaying interactive topic-based text summaries
US7451395B2 (en) 2002-12-16 2008-11-11 Palo Alto Research Center Incorporated Systems and methods for interactive topic-based text summarization
US20040122657A1 (en) * 2002-12-16 2004-06-24 Brants Thorsten H. Systems and methods for interactive topic-based text summarization
US7376893B2 (en) 2002-12-16 2008-05-20 Palo Alto Research Center Incorporated Systems and methods for sentence based interactive topic-based text summarization
US20040117740A1 (en) * 2002-12-16 2004-06-17 Chen Francine R. Systems and methods for displaying interactive topic-based text summaries
US20040117725A1 (en) * 2002-12-16 2004-06-17 Chen Francine R. Systems and methods for sentence based interactive topic-based text summarization
US20050149316A1 (en) * 2003-03-14 2005-07-07 Fujitsu Limited Translation support device
US7930166B2 (en) * 2003-03-14 2011-04-19 Fujitsu Limited Translation support device
US20040193571A1 (en) * 2003-03-31 2004-09-30 Ricoh Company, Ltd. Multimedia document sharing method and apparatus
US7536638B2 (en) 2003-03-31 2009-05-19 Ricoh Co., Ltd. Action stickers for identifying and processing stored documents
US7552381B2 (en) 2003-03-31 2009-06-23 Ricoh Co., Ltd. Check boxes for identifying and processing stored documents
US20050022122A1 (en) * 2003-03-31 2005-01-27 John Barrus Document collection manipulation
US20050162686A1 (en) * 2003-03-31 2005-07-28 Barrus John W. Check boxes for identifying and processing stored documents
US20060262995A1 (en) * 2003-03-31 2006-11-23 John Barrus Action stickers for identifying and processing stored documents
US7757162B2 (en) 2003-03-31 2010-07-13 Ricoh Co. Ltd. Document collection manipulation
US7739583B2 (en) 2003-03-31 2010-06-15 Ricoh Company, Ltd. Multimedia document sharing method and apparatus
US7509569B2 (en) 2003-03-31 2009-03-24 Ricoh Co., Ltd. Action stickers for nested collections
US7703002B2 (en) 2003-03-31 2010-04-20 Ricoh Company, Ltd. Method and apparatus for composing multimedia documents
US20070050696A1 (en) * 2003-03-31 2007-03-01 Piersol Kurt W Physical key for accessing a securely stored digital document
US7357640B2 (en) 2003-07-02 2008-04-15 Drb Lit Ltd. Lock-In Training system
US20050003337A1 (en) * 2003-07-02 2005-01-06 Berman Dennis R. Lock-In Training system
US7275159B2 (en) 2003-08-11 2007-09-25 Ricoh Company, Ltd. Multimedia output device having embedded encryption functionality
US20050050344A1 (en) * 2003-08-11 2005-03-03 Hull Jonathan J. Multimedia output device having embedded encryption functionality
WO2005048120A1 (en) * 2003-11-07 2005-05-26 Motorola Inc. Text summarization
US20050144908A1 (en) * 2004-01-02 2005-07-07 Cvc Technologies, Inc. Apparatus for tightening and loosening caps on containers
US7779355B1 (en) 2004-03-30 2010-08-17 Ricoh Company, Ltd. Techniques for using paper documents as media templates
US20050233293A1 (en) * 2004-03-31 2005-10-20 Berman Dennis R Computer system configured to store questions, answers, and keywords in a database that is utilized to provide training to users
US20070009878A1 (en) * 2004-03-31 2007-01-11 Berman Dennis R Lock-in training system
US20070009873A1 (en) * 2004-03-31 2007-01-11 Berman Dennis R Lock-in training system
US20070009874A1 (en) * 2004-03-31 2007-01-11 Berman Dennis R Lock-in training system
US20070009876A1 (en) * 2004-03-31 2007-01-11 Drb Lit Ltd. Lock-in training system
US7390191B2 (en) 2004-03-31 2008-06-24 Drb Lit Ltd. Computer system configured to sequence multi-day training utilizing a database
US20050221267A1 (en) * 2004-03-31 2005-10-06 Berman Dennis R Methods of selecting Lock-In Training courses and sessions
US20070009875A1 (en) * 2004-03-31 2007-01-11 Berman Dennis R Lock-in training system
US20050282135A1 (en) * 2004-03-31 2005-12-22 Berman Dennis R Lock-in training method utilizing the entry of a portion of a keyword
US20050233292A1 (en) * 2004-03-31 2005-10-20 Berman Dennis R Computer system configured to sequence multi-day training utilizing a database
US20090023125A1 (en) * 2004-03-31 2009-01-22 Berman Dennis R Lock-in training system progress display
US7364432B2 (en) 2004-03-31 2008-04-29 Drb Lit Ltd. Methods of selecting Lock-In Training courses and sessions
US20050262214A1 (en) * 2004-04-27 2005-11-24 Amit Bagga Method and apparatus for summarizing one or more text messages using indicative summaries
US8868670B2 (en) * 2004-04-27 2014-10-21 Avaya Inc. Method and apparatus for summarizing one or more text messages using indicative summaries
US20090276817A1 (en) * 2004-04-30 2009-11-05 Vulcan Inc. Management and non-linear presentation of music-related broadcasted or streamed multimedia content
US20060031879A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of news-related broadcasted or streamed multimedia content
US20060031916A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of broadcasted or streamed multimedia content
US20060031885A1 (en) * 2004-04-30 2006-02-09 Vulcan Inc. Management and non-linear presentation of music-related broadcasted or streamed multimedia content
US20050251743A1 (en) * 2004-05-10 2005-11-10 Fuji Xerox Co., Ltd. Learning apparatus, program therefor and storage medium
US20060085743A1 (en) * 2004-10-18 2006-04-20 Microsoft Corporation Semantic thumbnails
US7345688B2 (en) * 2004-10-18 2008-03-18 Microsoft Corporation Semantic thumbnails
US20060247599A1 (en) * 2005-04-29 2006-11-02 Kimberly-Clark Worldwide, Inc. Garment having an outer shell that freely moves in relation to an absorbent assembly therein
US8706618B2 (en) 2005-09-29 2014-04-22 Ebay Inc. Release of funds based on criteria
US20070073618A1 (en) * 2005-09-29 2007-03-29 Ebay Inc. Release of funds based on criteria
US8239358B1 (en) * 2007-02-06 2012-08-07 Dmitri Soubbotin System, method, and user interface for a search engine based on multi-document summarization
US7873640B2 (en) * 2007-03-27 2011-01-18 Adobe Systems Incorporated Semantic analysis documents to rank terms
US20080243820A1 (en) * 2007-03-27 2008-10-02 Walter Chang Semantic analysis documents to rank terms
US20110082863A1 (en) * 2007-03-27 2011-04-07 Adobe Systems Incorporated Semantic analysis of documents to rank terms
US8504564B2 (en) * 2007-03-27 2013-08-06 Adobe Systems Incorporated Semantic analysis of documents to rank terms
US20080270119A1 (en) * 2007-04-30 2008-10-30 Microsoft Corporation Generating sentence variations for automatic summarization
US20080281927A1 (en) * 2007-05-11 2008-11-13 Microsoft Corporation Summarization tool and method for a dialogue sequence
US8209617B2 (en) 2007-05-11 2012-06-26 Microsoft Corporation Summarization of attached, linked or related materials
US20080282159A1 (en) * 2007-05-11 2008-11-13 Microsoft Corporation Summarization of attached, linked or related materials
US20080320384A1 (en) * 2007-06-25 2008-12-25 Ramesh Nagarajan Automated addition of images to text
US20090210402A1 (en) * 2008-02-18 2009-08-20 Samsung Electronics Co. Ltd. System and method for contextual association discovery to conceptualize user query
US20100057710A1 (en) * 2008-08-28 2010-03-04 Yahoo! Inc Generation of search result abstracts
US8984398B2 (en) * 2008-08-28 2015-03-17 Yahoo! Inc. Generation of search result abstracts
US8874529B2 (en) * 2009-03-16 2014-10-28 Bert A. Silich User-determinable method and system for manipulating and displaying textual and graphical information
US20100235331A1 (en) * 2009-03-16 2010-09-16 Silich Bert A User-determinable method and system for manipulating and displaying textual and graphical information
US20120166940A1 (en) * 2010-12-28 2012-06-28 Elwha LLC, a limited liability company of the State of Delaware Multi-view graphical user interface for editing a base document with highlighting feature
US9355075B2 (en) * 2010-12-28 2016-05-31 Elwah LLC Multi-view graphical user interface for editing a base document with highlighting feature
US8488916B2 (en) * 2011-07-22 2013-07-16 David S Terman Knowledge acquisition nexus for facilitating concept capture and promoting time on task
US20130030792A1 (en) * 2011-07-26 2013-01-31 International Business Machines Corporation Customization of a Natural Language Processing Engine
US8725496B2 (en) * 2011-07-26 2014-05-13 International Business Machines Corporation Customization of a natural language processing engine
US9442928B2 (en) 2011-09-07 2016-09-13 Venio Inc. System, method and computer program product for automatic topic identification using a hypertext corpus
US9442930B2 (en) 2011-09-07 2016-09-13 Venio Inc. System, method and computer program product for automatic topic identification using a hypertext corpus
US20130151944A1 (en) * 2011-12-13 2013-06-13 Microsoft Corporation Highlighting of tappable web page elements
US9092131B2 (en) * 2011-12-13 2015-07-28 Microsoft Technology Licensing, Llc Highlighting of tappable web page elements
US8280888B1 (en) * 2012-05-04 2012-10-02 Pearl.com LLC Method and apparatus for creation of web document titles optimized for search engines
US9275038B2 (en) 2012-05-04 2016-03-01 Pearl.com LLC Method and apparatus for identifying customer service and duplicate questions in an online consultation system
US8463791B1 (en) 2012-05-04 2013-06-11 Pearl.com LLC Method and apparatus for creation of web document titles optimized for search engines
US9501580B2 (en) 2012-05-04 2016-11-22 Pearl.com LLC Method and apparatus for automated selection of interesting content for presentation to first time visitors of a website
US9646079B2 (en) 2012-05-04 2017-05-09 Pearl.com LLC Method and apparatus for identifiying similar questions in a consultation system

Also Published As

Publication number Publication date Type
JP3839069B2 (en) 2006-11-01 grant
JPH0736896A (en) 1995-02-07 application

Similar Documents

Publication Publication Date Title
Edmundson Problems in automatic abstracting
Kazama et al. Exploiting Wikipedia as external knowledge for named entity recognition
Rayson Matrix: A statistical method and software tool for linguistic analysis through corpus comparison
Reynar Topic segmentation: Algorithms and applications
US7117437B2 (en) Systems and methods for displaying interactive topic-based text summaries
US4980829A (en) Method and system for language translation
US6061675A (en) Methods and apparatus for classifying terminology utilizing a knowledge catalog
US7243305B2 (en) Spelling and grammar checking system
US5845143A (en) Language conversion system and text creating system using such
Breuel The OCRopus open source OCR system
US7251781B2 (en) Computer based summarization of natural language documents
US4864503A (en) Method of using a created international language as an intermediate pathway in translation between two national languages
US6182027B1 (en) Translation method and system
US7925498B1 (en) Identifying a synonym with N-gram agreement for a query phrase
US6571240B1 (en) Information processing for searching categorizing information in a document based on a categorization hierarchy and extracted phrases
US5278980A (en) Iterative technique for phrase query formation and an information retrieval system employing same
US7802184B1 (en) Method and apparatus for processing text and character data
US4862408A (en) Paradigm-based morphological text analysis for natural languages
US20040193401A1 (en) Linguistically informed statistical models of constituent structure for ordering in sentence realization for a natural language generation system
Pecina Lexical association measures and collocation extraction
US7475010B2 (en) Adaptive and scalable method for resolving natural language ambiguities
Trujillo Translation engines: techniques for machine translation
US20020032564A1 (en) Phrase-based dialogue modeling with particular application to creating a recognition grammar for a voice-controlled user interface
US20030182102A1 (en) Sentence realization model for a natural language generation system
US7092871B2 (en) Tokenizer for a natural language processing system

Legal Events

Date Code Title Description
AS Assignment

Owner name: XEROX CORPORATION, CONNECTICUT

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:WITHGOTT, M. MARGARET;CUTTING, DOUGLASS R.;REEL/FRAME:006619/0876

Effective date: 19930624

FPAY Fee payment

Year of fee payment: 4

FPAY Fee payment

Year of fee payment: 8

AS Assignment

Owner name: BANK ONE, NA, AS ADMINISTRATIVE AGENT, ILLINOIS

Free format text: SECURITY INTEREST;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:013153/0001

Effective date: 20020621

AS Assignment

Owner name: JPMORGAN CHASE BANK, AS COLLATERAL AGENT, TEXAS

Free format text: SECURITY AGREEMENT;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:015134/0476

Effective date: 20030625

Owner name: JPMORGAN CHASE BANK, AS COLLATERAL AGENT,TEXAS

Free format text: SECURITY AGREEMENT;ASSIGNOR:XEROX CORPORATION;REEL/FRAME:015134/0476

Effective date: 20030625

FPAY Fee payment

Year of fee payment: 12